基本信息
浏览量:53
职业迁徙
个人简介
My current research is centered around numerical optimization, notably for solving machine learning problems. More precisely, I’m interested in how to accelerate theoretically and/or pratically optimization methods.
The topics I mainly considered recently are:
T1- Inertial methods à la Nesterov to accelerate the convergence of rst order methods (e.g. the proximal
gradient) or more generally xed points of monotone operators – publications A8,A10,P4;
T2- Distributed optimization problems where the agents only have access to a local part of the problem
(e.g. data in machine learning, or partial oracles in optimization) and are coordinated in order to solve
a global problem – publications A9,A11,A13,P1;
T3- Randomized methods in which only a randomly selected part of the coordinates are updated at each
iteration in order to reduce the synchronization delay incurred by the computation of all the coordinates
(and thus reducing the exchanges in distributed systems) – publications A5,P2,P3.
The topics I mainly considered recently are:
T1- Inertial methods à la Nesterov to accelerate the convergence of rst order methods (e.g. the proximal
gradient) or more generally xed points of monotone operators – publications A8,A10,P4;
T2- Distributed optimization problems where the agents only have access to a local part of the problem
(e.g. data in machine learning, or partial oracles in optimization) and are coordinated in order to solve
a global problem – publications A9,A11,A13,P1;
T3- Randomized methods in which only a randomly selected part of the coordinates are updated at each
iteration in order to reduce the synchronization delay incurred by the computation of all the coordinates
(and thus reducing the exchanges in distributed systems) – publications A5,P2,P3.
研究兴趣
论文共 57 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
arxiv(2023)
Aleksandra Burashnikova,Yury Maximov,Marianne Clausel,Charlotte Laclau,Franck Iutzeler,Massih-Reza Amini
arXiv (Cornell University) (2022)
semanticscholar(2022)
引用0浏览0引用
0
0
International Symposium on Mathematical Programmingno. 1 (2022): 37-70
JOURNAL OF MACHINE LEARNING RESEARCH (2022)
引用0浏览0引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn